Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to size and dimension

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.74
    ario
    -0.73
    VPN
    -0.67
    ideo
    -0.67
    SEA
    -0.65
    ingham
    -0.65
    venient
    -0.65
    endez
    -0.65
    orious
    -0.64
    onto
    -0.63
    POSITIVE LOGITS
     sized
    0.88
     millenn
    0.82
     eleph
    0.81
     scale
    0.80
     intestine
    0.78
     therap
    0.78
    sized
    0.75
    hearted
    0.75
     proportions
    0.74
    gest
    0.74
    Act Density 0.011%

    No Known Activations